mcp-codex-worker: Skill for Claude Code

.claude/skills/worker-proof-and-analysis-toolkit/SKILL.md

worker-proof-and-analysis-toolkit is a skill for Claude Code from sorryorc/mcp-codex-worker. It costs 30 tokens per session (221 once invoked), scanned A, original, MIT.

A collection of methods for testing reliability ideas with explicit mechanisms, measurable predictions, controlled comparisons, and recorded negative results.

In plain words
What is it for?
Use it to investigate cases where automated checks passed but review found a problem, classify the cause, add regression coverage, and decide whether a warning should become enforcement.
Why use it?
It replaces confidence based only on model-written explanations with evidence from tests and measured jobs. It also helps assess the cost of false alarms before making a check block work.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sorryorc/mcp-codex-worker's own configuration. It tells Claude Code how to work on mcp-codex-worker itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-codex-worker configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sorryorc/mcp-codex-worker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sorryorc/mcp-codex-worker/main/.claude/skills/worker-proof-and-analysis-toolkit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sorryorc/mcp-codex-worker

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for worker-proof-and-analysis-toolkit

README.md
[![agentmods](https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-proof-and-analysis-toolkit.svg)](https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-proof-and-analysis-toolkit)
Your own site
<a href="https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-proof-and-analysis-toolkit"><img src="https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-proof-and-analysis-toolkit.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 221 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00221
Opus 5 $0.00015 $0.00111
Sonnet 5 $0.00006 $0.00044
Haiku 4.5 $0.00003 $0.00022

Measured 7d ago against content hash 9f7a16eebcca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

worker-proof-and-analysis-toolkit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/worker-proof-and-analysis-toolkit/SKILL.md · 41 lines

What it actually says

Worker Proof And Analysis Toolkit

Recipes

Hypothesis To Numbers

  • State the mechanism.
  • Predict which metric changes and by how much.
  • Run the smallest controlled comparison.
  • Keep negative evidence.

Semantic Failure Audit

  • Pick jobs where checks passed but review disagreed.
  • Classify root cause: missing context, wrong tool, weak model, or bad acceptance criteria.
  • Add a test or episode fixture for the class.

Blocking Risk Review

  • Estimate false positive cost.
  • Prefer observe mode until measured.
  • Promote to warn, then enforce only after regression coverage exists.

When Not To Use

Do not use this for routine feature implementation. Use worker-change-control.

Verification

  • npm run stats -- --since-minutes=60
  • npm test

Provenance and maintenance

Retire disproven hypotheses in docs or tests so they are not rediscovered.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 41 lines · 30 tokens per session scan A 9f7a16eebcca

Subscribe to this mod's changes

worker-proof-and-analysis-toolkit is a skill published in the GitHub repository sorryorc/mcp-codex-worker (2 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 221 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.